AI 中文总结
该研究提出Gwhere框架，结合SID生成与LLM生成式下一个POI推荐，经实验验证其在高德地图中可提升P-CTR和U-CTR，已部署应用且效果显著。
AI 中文摘要
生成式检索使推荐系统能够通过生成紧凑的物品标识符来检索物品，但由于冗余或冲突的标记分配，以及对异构物品信号的整合不足，将其扩展到工业场景仍具挑战性。这些挑战对于下一个兴趣点（POI）推荐尤为关键，其中模型必须表示结构化空间实体、捕捉序列移动模式，并生成符合真实用户行为的预测。我们提出Gwhere，一个端到端的工业框架，将语义标识符（SID）生成与基于大语言模型（LLM）的生成式下一个POI推荐相结合。Gwhere首先通过对比残差量化分词器学习具有区分性的POI SID，该分词器对齐文本、视觉、空间和协同信号。基于这些SID，Gwhere通过在丰富的时空语料库上进行持续预训练、监督微调，以及用于行为偏好对齐的强化学习目标——暴露感知卡尼曼-特沃斯基优化（EAKTO），使LLM适配移动场景。在公开数据集和高德地图的大规模工业数据集上的实验证明了Gwhere的有效性。该系统已部署在高德地图主页服务中，满足高并发和低延迟约束。长期在线A/B测试显示，相比生产基线，P-点击率（P-CTR）提升5.83%，用户点击率（U-CTR）提升6.20%。其实现可在指定URL获取。
英文摘要
Generative retrieval enables recommender systems to retrieve items by generating compact item identifiers, but scaling it to industrial scenarios remains challenging due to redundant or colliding token assignments and insufficient integration of heterogeneous item signals. These challenges are particularly critical for next Point-of-Interest (POI) recommendation, where models must represent structured spatial entities, capture sequential mobility patterns, and produce predictions consistent with real user behavior. We propose Gwhere, an end-to-end industrial framework that integrates semantic identifier (SID) generation with LLM-based generative next POI recommendation. Gwhere first learns discriminative POI SIDs through a contrastive residual-quantization tokenizer that aligns textual, visual, spatial, and collaborative signals. Based on these SIDs, Gwhere adapts LLMs to mobility scenarios via continued pretraining on enriched spatio-temporal corpora, supervised fine-tuning, and Exposure-Aware Kahneman-Tversky Optimization (EAKTO), a reinforcement learning objective for behavioral preference alignment. Experiments on public datasets and Amap's large-scale industrial dataset demonstrate the effectiveness of Gwhere. The system has been deployed in Amap's homepage service under high-concurrency and low-latency constraints. Long-term online A/B tests show improvements of 5.83% in P-CTR and 6.20% in U-CTR over the production baseline. The implementation is publicly available at https://github.com/alibaba/SimCIT.
Comments10 pages, 4 figures
